CN110532969B - Slope unit dividing method based on multi-scale image segmentation - Google Patents
Slope unit dividing method based on multi-scale image segmentation Download PDFInfo
- Publication number
- CN110532969B CN110532969B CN201910823312.5A CN201910823312A CN110532969B CN 110532969 B CN110532969 B CN 110532969B CN 201910823312 A CN201910823312 A CN 201910823312A CN 110532969 B CN110532969 B CN 110532969B
- Authority
- CN
- China
- Prior art keywords
- slope
- unit
- segmentation
- layer
- axis direction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Abstract
The invention discloses a slope unit dividing method based on multi-scale image segmentation, which comprises the steps of obtaining a slope layer based on a digital elevation model; calculating to obtain a unit vector in the X-axis direction and a unit vector in the Y-axis direction, and taking the unit vectors as main body segmentation layers for dividing the slope units; extracting a water collecting area layer and taking the water collecting area layer as a limiting layer divided by a slope unit; and dividing the slope unit to obtain a final slope unit division result. The method comprises the steps of establishing a data set suitable for multi-scale segmentation, an optimal segmentation scale and a segmentation algorithm by comprehensively considering topographic factors, and generating a suitable slope unit; therefore, the method can provide reliable map unit support for geological disaster risk evaluation, and the slope unit dividing method is high in reliability and high in dividing precision of the slope units.
Description
Technical Field
The invention particularly relates to a slope unit dividing method based on multi-scale image segmentation.
Background
Regional geological disaster risk evaluation can predict the probability of geological disaster in a large range. The key step of regional geological disaster risk evaluation is the determination of map units, and the reasonable selection and division of the map units directly influence the quality of risk evaluation results.
The most commonly used geological disaster evaluation units include grid cells and ramp cells. Wherein: the division of the grid units directly divides the research area into square grids with equal size, the shape is regular, the subdivision is simple and easy to implement, the data in the form of a matrix obtained after the dispersion is also beneficial to further operation, but the grid units are not easy to present the spatial correlation between landforms and can not reflect the landform characteristics; the slope units are divided into the same units by dividing the adjacent similar terrains, the units are influenced by boundary conditions and microtopography, can be regarded as near-homogeneous terrain units which are basic units for development of landslide, collapse and other geological disasters, can be closely related to geological environment conditions, comprehensively reflect the effects of various control or influence factors, and enable the evaluation results to be closer to reality.
The traditional slope unit dividing method is usually used for surveying and mapping in the field or using a stereo aerial image pair, and slope units are identified and classified manually, but the processing process of the method is complicated and time-consuming, so that some scholars try to develop an automatic terrain classification program by using a digital elevation model. The automatic division saves time and labor and cost, can effectively reduce manual errors, avoids the limitation of different experiences and subjective standards of different operators, can ensure the consistency of division results, and has obvious advantages compared with manual division. At present, the most widely applied automatic slope unit dividing method is a traditional catchment area overlapping method, namely, a hydrological analysis module ArcHydro based on an ArcGIS platform firstly carries out once catchment area analysis to obtain a valley line; then, reversing the height value of the numerical elevation model, and performing second water collecting area analysis, so that the original water system can be reversed to a ridge line; then, the valley line and the ridge line are crossed, and the original water collecting area can be cut into a left slope unit and a right slope unit. However, the dividing process of the method is complicated, the subjective dependence on the determination of the water collection area threshold value in the dividing process is high, the unified standard is lacked, the generated water collection area unit is easy to generate more fine broken surfaces and unreasonable strip-shaped surfaces, and a large amount of manual modification is needed in the later stage.
Disclosure of Invention
The invention aims to provide a slope unit dividing method based on multi-scale image segmentation, which is high in reliability and high in precision.
The invention provides a slope unit dividing method based on multi-scale image segmentation, which comprises the following steps:
s1, obtaining a slope map layer based on a digital elevation model;
s2, calculating to obtain a unit vector in the X-axis direction and a unit vector in the Y-axis direction according to the slope layer data acquired in the step S1, and taking the unit vector in the X-axis direction and the unit vector in the Y-axis direction as main body partition layers for partitioning a slope unit;
s3, extracting a water collecting region layer, and using the extracted water collecting region layer as a limiting layer divided by a slope unit;
and S4, dividing the slope unit according to the main body division layer obtained in the step S2 and the limitation layer obtained in the step S3, so as to obtain a final slope unit division result.
The slope unit dividing method based on the multi-scale image segmentation further comprises the following steps:
s5, constructing a segmentation precision evaluation function by adopting the local variance and the Moran index, and evaluating the slope unit division result of the method.
And S1, obtaining a slope layer based on the digital elevation model, specifically obtaining the slope layer through ArcGIS pretreatment based on the digital elevation model, and using the slope layer as a data set for automatically dividing slope units.
Step S2 is to calculate to obtain a unit vector in the X-axis direction and a unit vector in the Y-axis direction according to the slope layer data obtained in step S1, specifically, to convert the slope layer data obtained in step S1 into radian slope making data, and then to perform trigonometric function calculation, so as to obtain a unit vector in the X-axis direction and a unit vector in the Y-axis direction.
The unit vector in the X-axis direction and the unit vector in the Y-axis direction are obtained by calculation through the following steps:
A. converting the slope layer data into radian data theta by adopting the following formula:
in the formula, alpha is slope layer data;
B. performing trigonometric function calculation on the data obtained in the step A by adopting the following formula to obtain a unit vector in the X-axis direction
Unit vector in Y-axis direction
And in the formula, theta is radian data obtained in the step A.
Step S3, extracting the water collection area map layer specifically includes the following steps:
a. filling depression in DEM data so as to avoid flow direction abnormity;
b. analyzing the flow direction, and calculating the flow direction of the grids and the accumulated flow received by each grid;
c. determining an optimal accumulated flow threshold value by taking an actual water system as a reference, and obtaining the water system with the accumulated flow higher than the threshold value;
d. and (4) carrying out river segmentation, dividing the water system into different river sections, and carrying out water collection area calculation to obtain a final water collection area map layer.
Step S4, the slope unit is divided, specifically, the following steps are adopted for dividing:
(1) Setting an initial segmentation scale (it is recommended to set a smaller initial segmentation size), and calculating the standard deviation in the neighborhood corresponding to the set initial segmentation scale by using the following formula:
in the formula sigma i The standard deviation in the neighborhood of the ith set size; n is the number of pixels contained in a neighborhood with a set size; c. C i Is the gray value of the ith pixel;
the average value of pixel gray values in the neighborhood of the ith set size is obtained;
(2) Calculating the mean value of the standard deviation in each neighborhood with set size except the edge by adopting the following formula, wherein the mean value is the LV (Local-variance) value of the object layer:
wherein m is the number of neighborhoods with set sizes participating in calculation in the whole target layer;
(3) Amplifying the initial segmentation scale set in the step (1) according to a set scaling parameter, and calculating LV values under different neighborhood sizes; the division layers where the neighborhoods with different sizes are located are the different target layers;
(4) Calculating the local variance change rate ROC-LV (ROC-LV, rates of change of LV) between different target layers by adopting the following formula:
wherein L is the LV value of the target layer, and L-1 is the LV value of the next target layer;
(5) Measuring the LV variable quantity from one target layer to another target layer by adopting the local variance change rate obtained in the step (4), and when the LV variable quantity is maximum, selecting a segmentation scale corresponding to the LV variable quantity as an optimal segmentation scale, namely the segmentation scale corresponding to the peak point of ROC-LV;
(6) And determining other two parameters required by multi-scale segmentation by adopting a control variable method through experiments: shape factor, compactness factor;
(7) And taking the unit vector in the X-axis direction and the unit vector in the Y-axis direction of the slope layer as main body segmentation layers, taking the water collection region layer as a terrain condition limiting boundary, and taking the optimal segmentation scale, shape factor and compactness factor as segmentation parameters to perform multi-scale segmentation, thereby obtaining a final slope unit segmentation result.
In step S5, the local variance and the Moran index are used to construct a segmentation accuracy evaluation function, specifically, the following formula is used as the segmentation accuracy evaluation function F (V, I):
in the formula V max Is the maximum value of V; v min Is the minimum value of V; i is max Is the maximum value of I; i is min Is the minimum value of I; v is a first intermediate parameter and is defined as
s n Is the area of the nth cell, c n Is the slope variance inside the nth cell
q is the number of picture elements in the unit, p i Is the slope value corresponding to the ith pixel element,
the mean value of the slope values of the pixels in the unit; i is a second intermediate parameter and is defined as
N is the number of units, alpha n Is the slope mean value in the nth cell, alpha l Is the slope mean, ω, in the l-th cell n,l Is a spatial proximity relation index, and ω is a value when the nth cell is adjacent to the lth cell n,l The value is 1, when the nth unit is not adjacent to the first unit, omega n,l The value of the oxygen is 0, and the oxygen concentration is less than or equal to zero,
and the average value of the slope direction of the image layer is shown.
The slope unit dividing method based on multi-scale image segmentation provided by the invention establishes a data set suitable for multi-scale segmentation, an optimal segmentation scale and a segmentation algorithm by comprehensively considering terrain elements, and generates a suitable slope unit; therefore, the method can provide reliable map unit support for geological disaster risk evaluation, and the slope unit dividing method is high in reliability and high in dividing precision of the slope units.
Drawings
FIG. 1 is a schematic process flow diagram of the process of the present invention.
FIG. 2 is a schematic diagram of the slope direction and the conversion into unit vector of the method of the present invention.
FIG. 3 is a schematic diagram of the calculation of the optimal segmentation scale according to the method of the present invention.
FIG. 4 is a diagram illustrating the comparison of the precision of the slope unit division results between the method of the present invention and the conventional method.
Detailed Description
FIG. 1 is a schematic flow chart of the method of the present invention: the invention provides a slope unit dividing method based on multi-scale image segmentation, which comprises the following steps:
s1, obtaining a slope map layer based on a digital elevation model; specifically, a slope map layer is obtained through ArcGIS pretreatment based on a digital elevation model, so that a data set of a slope unit is automatically divided;
s2, calculating to obtain a unit vector in the X-axis direction and a unit vector in the Y-axis direction according to the slope layer data acquired in the step S1, and taking the unit vector in the X-axis direction and the unit vector in the Y-axis direction as main body partition layers for partitioning a slope unit; converting the slope layer data acquired in the step S1 into radian system slope data, and then performing trigonometric function calculation to obtain a unit vector in the X-axis direction and a unit vector in the Y-axis direction;
since the slope data α has periodic continuity, as shown in fig. 2: the actual directions represented by 0 ° and 359 ° differ by only 1 degree, but are 359 ° numerically. In order to avoid the problem caused by the overlarge difference between the values around the slope 0 degree when the image is divided and the blocks are merged, the unit vector is calculated by adopting the following steps:
A. converting the slope layer data into radian data theta by adopting the following formula:
in the formula, alpha is slope layer data;
B. performing trigonometric function calculation on the data obtained in the step A by adopting the following formula to obtain a unit vector in the X-axis direction
Unit vector in Y-axis direction
In the formula, theta is radian data obtained in the step A;
s3, extracting a water collecting region layer, and using the extracted water collecting region layer as a limiting layer divided by a slope unit; specifically, the water collecting area map layer is extracted by the following steps:
a. filling depression in DEM data so as to avoid flow direction abnormity;
b. analyzing the flow direction, and calculating the flow direction of the grids and the accumulated flow received by each grid;
c. determining an optimal accumulated flow threshold value by taking an actual water system as a reference, and obtaining the water system with the accumulated flow higher than the threshold value;
d. carrying out river segmentation, dividing a water system into different river sections, and carrying out water collection area calculation to obtain a final water collection area map layer;
and S4, dividing the slope unit according to the main body division layer obtained in the step S2 and the limiting layer obtained in the step S3, so as to obtain a final slope unit division result. The method comprises the following steps:
(1) Setting an initial segmentation scale (it is recommended to set a smaller initial segmentation size), and calculating the standard deviation in the neighborhood corresponding to the set initial segmentation scale by using the following formula:
in the formula sigma i The standard deviation in the neighborhood of the ith set size; n is the number of pixels contained in a neighborhood with a set size; c. C i Is the gray value of the ith pixel;
the average value of pixel gray values in the neighborhood of the ith set size is obtained;
(2) Calculating the mean value of the standard deviation in each neighborhood with set size except the edge by adopting the following formula, wherein the mean value is the LV (Local-variance) value of the object layer:
wherein m is the number of neighborhoods with set sizes participating in calculation in the whole target layer;
(3) Amplifying the initial segmentation scale set in the step (1) according to a set scaling parameter, and calculating LV values under different neighborhood sizes; the partition layers where the neighborhoods with different sizes are located are the different target layers;
(4) Calculating the local variance change rate ROC-LV (ROC-LV, rates of change of LV) between different target layers by adopting the following formula:
wherein L is the LV value of the target layer, and L-1 is the LV value of the next target layer;
(5) Measuring the LV variable quantity from one target layer to another target layer by adopting the local variance change rate obtained in the step (4), and when the LV variable quantity is maximum, selecting a segmentation scale corresponding to the LV variable quantity as an optimal segmentation scale, namely the segmentation scale corresponding to the peak point of ROC-LV;
(6) And (3) determining two other parameters required by multi-scale segmentation by adopting a control variable method through experiments: shape factor, compactness factor;
(7) Taking the unit vector in the X-axis direction and the unit vector in the Y-axis direction of the slope layer as main body segmentation layers, taking the water collection region layer as a terrain condition limiting boundary, and taking the optimal segmentation scale, shape factor and compactness factor as segmentation parameters to perform multi-scale segmentation, so as to obtain a final slope unit segmentation result;
s5, constructing a segmentation precision evaluation function by adopting a local variance and a Moran index, and evaluating a slope unit division result of the method; specifically, the following formula is adopted as the segmentation accuracy evaluation function F (V, I):
in the formula V max Is the maximum value of V; v min Is the minimum value of V; i is max Is the maximum value of I; i is min Is the minimum value of I; v is a first intermediate parameter and is defined as
s n Is the area of the nth cell, c n Is the slope variance inside the nth cell
q is the number of pixels in the unit, p i Is the slope value corresponding to the ith pixel element,
the mean value of the slope values of the pixels in the unit; i is a second intermediate parameter and is defined as
N is the number of units, alpha n Is the slope mean value in the nth cell, alpha l Is the slope mean value in the l unit, ω n,l Is a spatial proximity index, and ω is a value when the nth cell is adjacent to the first cell n,l The value is 1, when the nth unit is not adjacent to the first unit, omega n,l The value of the oxygen is 0, and the oxygen concentration is less than or equal to zero,
the mean value of the slope direction of the map layer is shown; when the radian data theta and the unit vector of the X-axis direction are measured
Unit vector in Y-axis direction
Substituting into the formula of I, so that the parameters in the formula of I are rewritten as follows:
and calculating the F (V, I) value of each slope unit according to the formula, and then drawing a box type graph capable of describing data distribution characteristics according to the calculation result so as to compare the dividing precision of the slope units obtained by the traditional water collecting area overlapping method and the method disclosed by the invention. The evaluation function is based on the dividing principle of the slope units, and when the homogeneity in the units is highest and the heterogeneity between the units is highest, the dividing result of the slope units is the best. The local variance is used as a unit internal homogeneity measurement index in the evaluation function, and the smaller the index value is, the higher the internal homogeneity is represented; the magnitude of heterogeneity among units is measured by using a Moran index, and the smaller the index is, the higher heterogeneity among units is represented. Therefore, according to the F (V, I) calculation principle, the larger the F (V, I) value is, the higher the homogeneity inside the unit obtained by the division is, and the higher the heterogeneity between units is, that is, the higher the division precision is.
Example results are shown in the median and bin data distribution plots of FIG. 4. It can be seen that the minimum value of F (V, I) corresponding to the multi-scale image segmentation method for dividing the slope unit is 0.3466, the median is 1.3108, and the minimum value 0.2174 and the median 1.2312 which are both larger than those of the minimum value and the median calculated by the traditional water collecting area overlapping method indicate that the method is better in division result and higher in division precision compared with the traditional water collecting area overlapping method.
Claims (7)
1. A slope unit dividing method based on multi-scale image segmentation comprises the following steps:
s1, obtaining a slope map layer based on a digital elevation model;
s2, calculating to obtain a unit vector in the X-axis direction and a unit vector in the Y-axis direction according to the slope layer data acquired in the step S1, and taking the unit vector in the X-axis direction and the unit vector in the Y-axis direction as main body partition layers for partitioning a slope unit;
s3, extracting a water collecting region layer, and using the extracted water collecting region layer as a limiting layer divided by a slope unit;
s4, dividing the slope unit according to the main body division layer obtained in the step S2 and the limiting layer obtained in the step S3, so as to obtain a final slope unit division result; the method comprises the following steps:
(1) Setting an initial segmentation scale, and calculating the standard deviation in the neighborhood corresponding to the set initial segmentation scale by adopting the following formula:
in the formula σ i The standard deviation in the neighborhood of the ith set size; n is the number of pixels contained in a neighborhood with a set size; c. C i Is the gray value of the ith pixel;
the average value of pixel gray values in the neighborhood of the ith set size is obtained;
(2) Calculating the mean value of the standard deviations in each neighborhood with set size except the edge by adopting the following formula, wherein the mean value is the LV value of the object layer:
wherein m is the number of neighborhoods with set sizes participating in calculation in the whole target layer;
(3) Amplifying the initial segmentation scale set in the step (1) according to a set scaling parameter, and calculating LV values under different neighborhood sizes; the division layers where the neighborhoods with different sizes are located are different target layers;
(4) Calculating the local variance change rate ROC-LV between different target layers by adopting the following formula:
wherein L is the LV value of the target layer, and L-1 is the LV value of the next target layer;
(5) Measuring the LV variable quantity from one target layer to another target layer by adopting the local variance change rate obtained in the step (4), and when the LV variable quantity is maximum, selecting a segmentation scale corresponding to the LV variable quantity as an optimal segmentation scale, namely the segmentation scale corresponding to the peak point of ROC-LV;
(6) And determining other two parameters required by multi-scale segmentation by adopting a control variable method through experiments: shape factor, compactness factor;
(7) And taking the unit vector in the X-axis direction and the unit vector in the Y-axis direction of the slope layer as main body segmentation layers, taking the water collection region layer as a terrain condition limiting boundary, and taking the optimal segmentation scale, shape factor and compactness factor as segmentation parameters to perform multi-scale segmentation, thereby obtaining a final slope unit segmentation result.
2. The ramp unit partitioning method based on multi-scale image segmentation according to claim 1, further comprising the steps of:
and S5, constructing a segmentation precision evaluation function by adopting the local variance and the Moran index, and evaluating the slope unit segmentation result.
3. The method for dividing the slope unit based on multi-scale image segmentation according to claim 1, wherein the step S1 is performed by obtaining a slope layer based on the digital elevation model, specifically, obtaining the slope layer based on the digital elevation model through ArcGIS preprocessing, so as to automatically divide the data set of the slope unit.
4. The method for dividing a slope unit based on multi-scale image segmentation according to claim 1, wherein in step S2, a unit vector in an X-axis direction and a unit vector in a Y-axis direction are obtained through calculation according to the slope layer data obtained in step S1, specifically, the slope layer data obtained in step S1 is converted into radian-based slope data, and then trigonometric function calculation is performed, so as to obtain the unit vector in the X-axis direction and the unit vector in the Y-axis direction.
5. The slope unit dividing method based on multi-scale image segmentation as claimed in claim 4, wherein the calculating obtains the unit vector in the X-axis direction and the unit vector in the Y-axis direction, specifically, the calculating obtains the unit vectors by using the following steps:
A. converting the slope layer data into radian data theta by adopting the following formula:
in the formula, alpha is slope layer data;
B. performing trigonometric function calculation on the data obtained in the step A by adopting the following formula to obtain a unit vector in the X-axis direction
Unit vector in Y-axis direction
And in the formula, theta is radian data obtained in the step A.
6. The slope unit dividing method based on multi-scale image segmentation according to claim 1, wherein the step S3 of extracting the water-collecting region image layer specifically comprises the following steps of:
a. depression filling is carried out on DEM data, so that abnormal flow direction is avoided;
b. analyzing the flow direction, and calculating the flow direction of the grids and the accumulated flow received by each grid;
c. determining an optimal accumulated flow threshold value by taking an actual water system as a reference, and obtaining the water system with the accumulated flow higher than the threshold value;
d. and (4) carrying out river segmentation, dividing the water system into different river sections, and carrying out water collection area calculation to obtain a final water collection area map layer.
7. The slope unit dividing method based on multi-scale image segmentation according to claim 2, wherein the local variance and Moran index are used to construct the segmentation accuracy evaluation function in step S5, specifically, the following formula is used as the segmentation accuracy evaluation function F (V, I):
in the formula V max Is the maximum value of V; v min Is the minimum value of V; i is max Is the maximum value of I; i is min Is the minimum value of I; v is a first intermediate parameter and is defined as
s n Is the area of the nth cell, c n Is the slope variance inside the nth cell
q is the number of picture elements in the unit, p i Is the slope value corresponding to the ith pixel element,
the average value of the slope values of the pixels in the unit is obtained; i is a second intermediate parameter and is defined as
N is the number of units, alpha n Is the slope mean value in the nth cell, alpha l Is the slope mean, ω, in the l-th cell n,l Is a spatial proximity relation index, and ω is a value when the nth cell is adjacent to the lth cell n,l The value is 1, when the nth unit is not adjacent to the first unit, omega n,l The value of the oxygen is 0, and the oxygen concentration is less than or equal to zero,
and the mean value of the slope direction of the map layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823312.5A CN110532969B (en) | 2019-09-02 | 2019-09-02 | Slope unit dividing method based on multi-scale image segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910823312.5A CN110532969B (en) | 2019-09-02 | 2019-09-02 | Slope unit dividing method based on multi-scale image segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110532969A CN110532969A (en) | 2019-12-03 |
| CN110532969B true CN110532969B (en) | 2022-12-27 |
Family
ID=68666186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910823312.5A Active CN110532969B (en) | 2019-09-02 | 2019-09-02 | Slope unit dividing method based on multi-scale image segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110532969B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113850822B (en) * | 2021-09-18 | 2023-04-25 | 四川大学 | Automatic slope unit dividing method based on confluence division |
| CN114329663B (en) * | 2021-12-27 | 2022-08-05 | 中国自然资源航空物探遥感中心 | Slope unit dividing method based on scale of historical geological disasters |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455711A (en) * | 2013-08-15 | 2013-12-18 | 广州地理研究所 | Small watershed region-oriented landslide hazard risk division method based on mechanism analysis |
| CN104820826A (en) * | 2015-04-27 | 2015-08-05 | 重庆大学 | Digital elevation model-based slope form extraction and recognition method |
| WO2016032398A2 (en) * | 2014-08-25 | 2016-03-03 | Singapore University Of Technology And Design | Method and device for analysing an image |
-
2019
- 2019-09-02 CN CN201910823312.5A patent/CN110532969B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103455711A (en) * | 2013-08-15 | 2013-12-18 | 广州地理研究所 | Small watershed region-oriented landslide hazard risk division method based on mechanism analysis |
| WO2016032398A2 (en) * | 2014-08-25 | 2016-03-03 | Singapore University Of Technology And Design | Method and device for analysing an image |
| CN104820826A (en) * | 2015-04-27 | 2015-08-05 | 重庆大学 | Digital elevation model-based slope form extraction and recognition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110532969A (en) | 2019-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446616B (en) | Road extraction method based on full convolution neural network ensemble learning | |
| CN116167668B (en) | BIM-based green energy-saving building construction quality evaluation method and system | |
| CN110532969B (en) | Slope unit dividing method based on multi-scale image segmentation | |
| CN108153979B (en) | Deformation information extraction method based on InSAR, terminal and storage medium | |
| CN110597873A (en) | Precipitation data estimation method, precipitation data estimation device, precipitation data estimation equipment and storage medium | |
| CN109389553B (en) | Meteorological facsimile picture contour interpolation method based on T spline | |
| CN112131731B (en) | Urban growth cellular simulation method based on spatial feature vector filtering | |
| CN109613531B (en) | Multi-threshold optimization deformation inversion method and system for micro-variation perception early warning radar | |
| CN109190593B (en) | Mountain road side slope stability preliminary discrimination method along line based on concave-convex classification | |
| CN114822033A (en) | Road network traffic flow data restoration method and system based on characteristic pyramid network | |
| CN111982077B (en) | Electronic map drawing method and system and electronic equipment | |
| CN116051777B (en) | Super high-rise building extraction method, apparatus and readable storage medium | |
| CN115147726B (en) | City form map generation method and device, electronic equipment and readable storage medium | |
| CN114202551B (en) | Grading drawing method and grading drawing device for karst stony desertification | |
| CN110533663B (en) | Image parallax determining method, device, equipment and system | |
| CN115861816A (en) | Three-dimensional low vortex identification method and device, storage medium and terminal | |
| CN113850822B (en) | Automatic slope unit dividing method based on confluence division | |
| CN115937676A (en) | Large-scale sand dune landform fine classification method based on DEM | |
| CN115630577A (en) | Downscaling rainfall prediction method and system | |
| CN115757365A (en) | Multi-dimensional time sequence data anomaly detection method, model training method and device | |
| CN113762153B (en) | Novel tailing pond detection method and system based on remote sensing data | |
| Lussana et al. | Evaluation of seNorge2, a conventional climatological datasets for snow-and hydrological modeling in Norway | |
| CN117036959B (en) | Building flood vulnerability evaluation method based on remote sensing | |
| CN113807724B (en) | Site selection method for slag disposal site based on comprehensive risk evaluation | |
| CN116385683B (en) | Three-dimensional small drainage basin channel fractal dimension calculation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |